transformers/tests/utils/test_activations.py

74 lines
2.5 KiB
Python
Raw Normal View History

# Copyright 2020 The HuggingFace Team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import unittest
from transformers import is_torch_available
from transformers.testing_utils import require_torch
if is_torch_available():
import torch
from transformers.activations import gelu_new, gelu_python, get_activation
@require_torch
class TestActivations(unittest.TestCase):
def test_gelu_versions(self):
x = torch.tensor([-100, -1, -0.1, 0, 0.1, 1.0, 100])
torch_builtin = get_activation("gelu")
self.assertTrue(torch.allclose(gelu_python(x), torch_builtin(x)))
self.assertFalse(torch.allclose(gelu_python(x), gelu_new(x)))
def test_gelu_10(self):
x = torch.tensor([-100, -1, -0.1, 0, 0.1, 1.0, 100])
torch_builtin = get_activation("gelu")
gelu10 = get_activation("gelu_10")
y_gelu = torch_builtin(x)
y_gelu_10 = gelu10(x)
clipped_mask = torch.where(y_gelu_10 < 10.0, 1, 0)
self.assertTrue(torch.max(y_gelu_10).item() == 10.0)
self.assertTrue(torch.allclose(y_gelu * clipped_mask, y_gelu_10 * clipped_mask))
def test_get_activation(self):
get_activation("gelu")
get_activation("gelu_10")
Reformer (#3351) * first copy & past commit from Bert and morgans LSH code * add easy way to compare to trax original code * translate most of function * make trax lsh self attention deterministic with numpy seed + copy paste code * add same config * add same config * make layer init work * implemented hash_vectors function for lsh attention * continue reformer translation * hf LSHSelfAttentionLayer gives same output as trax layer * refactor code * refactor code * refactor code * refactor * refactor + add reformer config * delete bogus file * split reformer attention layer into two layers * save intermediate step * save intermediate step * make test work * add complete reformer block layer * finish reformer layer * implement causal and self mask * clean reformer test and refactor code * fix merge conflicts * fix merge conflicts * update init * fix device for GPU * fix chunk length init for tests * include morgans optimization * improve memory a bit * improve comment * factorize num_buckets * better testing parameters * make whole model work * make lm model work * add t5 copy paste tokenizer * add chunking feed forward * clean config * add improved assert statements * make tokenizer work * improve test * correct typo * extend config * add complexer test * add new axial position embeddings * add local block attention layer * clean tests * refactor * better testing * save intermediate progress * clean test file * make shorter input length work for model * allow variable input length * refactor * make forward pass for pretrained model work * add generation possibility * finish dropout and init * make style * refactor * add first version of RevNet Layers * make forward pass work and add convert file * make uploaded model forward pass work * make uploaded model forward pass work * refactor code * add namedtuples and cache buckets * correct head masks * refactor * made reformer more flexible * make style * remove set max length * add attention masks * fix up tests * fix lsh attention mask * make random seed optional for the moment * improve memory in reformer * add tests * make style * make sure masks work correctly * detach gradients * save intermediate * correct backprob through gather * make style * change back num hashes * rename to labels * fix rotation shape * fix detach * update * fix trainer * fix backward dropout * make reformer more flexible * fix conflict * fix * fix * add tests for fixed seed in reformer layer * fix trainer typo * fix typo in activations * add fp16 tests * add fp16 training * support fp16 * correct gradient bug in reformer * add fast gelu * re-add dropout for embedding dropout * better naming * better naming * renaming * finalize test branch * finalize tests * add more tests * finish tests * fix * fix type trainer * fix fp16 tests * fix tests * fix tests * fix tests * fix issue with dropout * fix dropout seeds * correct random seed on gpu * finalize random seed for dropout * finalize random seed for dropout * remove duplicate line * correct half precision bug * make style * refactor * refactor * docstring * remove sinusoidal position encodings for reformer * move chunking to modeling_utils * make style * clean config * make style * fix tests * fix auto tests * pretrained models * fix docstring * update conversion file * Update pretrained_models.rst * fix rst * fix rst * update copyright * fix test path * fix test path * fix small issue in test * include reformer in generation tests * add docs for axial position encoding * finish docs * Update convert_reformer_trax_checkpoint_to_pytorch.py * remove isort * include sams comments * remove wrong comment in utils * correct typos * fix typo * Update reformer.rst * applied morgans optimization * make style * make gpu compatible * remove bogus file * big test refactor * add example for chunking * fix typo * add to README
2020-05-07 16:17:01 +08:00
get_activation("gelu_fast")
get_activation("gelu_new")
get_activation("gelu_python")
get_activation("linear")
get_activation("mish")
get_activation("quick_gelu")
get_activation("relu")
get_activation("sigmoid")
get_activation("silu")
get_activation("swish")
get_activation("tanh")
with self.assertRaises(KeyError):
get_activation("bogus")
with self.assertRaises(KeyError):
get_activation(None)
def test_activations_are_distinct_objects(self):
act1 = get_activation("gelu")
act1.a = 1
act2 = get_activation("gelu")
self.assertEqual(act1.a, 1)
with self.assertRaises(AttributeError):
_ = act2.a